Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3537 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1577349 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1186828 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1900274 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3006. Min Act: -0.0000

Data Index: 498927 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1201776 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1415860 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.3021. Min Act: -0.0000

Data Index: 740188 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1218220 (The Pile)

Max Activating Token Index: 745

Text #8

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1218758 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2829. Min Act: -0.0000

Data Index: 703842 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2937. Min Act: -0.0000

Data Index: 532329 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1838481 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1355881 (The Pile)

Max Activating Token Index: 996

Text #13

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1213264 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1268090 (The Pile)

Max Activating Token Index: 634

Text #15

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1799763 (The Pile)

Max Activating Token Index: 302

Text #16

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2576. Min Act: -0.0000

Data Index: 149298 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1485754 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1696436 (The Pile)

Max Activating Token Index: 692

Text #19

Max Range: 0.3324. Min Range: -0.3324

Max Act: 0.2818. Min Act: -0.0000

Data Index: 1377471 (The Pile)

Max Activating Token Index: 573